sedrickkeh's picture
Training in progress, epoch 2
293c342 verified
{"current_steps": 1, "total_steps": 93, "loss": 0.8186, "lr": 2.0000000000000003e-06, "epoch": 0.032, "percentage": 1.08, "elapsed_time": "0:00:37", "remaining_time": "0:58:09"}
{"current_steps": 2, "total_steps": 93, "loss": 0.8458, "lr": 4.000000000000001e-06, "epoch": 0.064, "percentage": 2.15, "elapsed_time": "0:01:14", "remaining_time": "0:56:07"}
{"current_steps": 3, "total_steps": 93, "loss": 0.8188, "lr": 6e-06, "epoch": 0.096, "percentage": 3.23, "elapsed_time": "0:01:40", "remaining_time": "0:50:29"}
{"current_steps": 4, "total_steps": 93, "loss": 0.8172, "lr": 8.000000000000001e-06, "epoch": 0.128, "percentage": 4.3, "elapsed_time": "0:02:08", "remaining_time": "0:47:39"}
{"current_steps": 5, "total_steps": 93, "loss": 0.7248, "lr": 1e-05, "epoch": 0.16, "percentage": 5.38, "elapsed_time": "0:02:32", "remaining_time": "0:44:41"}
{"current_steps": 6, "total_steps": 93, "loss": 0.8667, "lr": 1.2e-05, "epoch": 0.192, "percentage": 6.45, "elapsed_time": "0:03:08", "remaining_time": "0:45:30"}
{"current_steps": 7, "total_steps": 93, "loss": 0.8164, "lr": 1.4e-05, "epoch": 0.224, "percentage": 7.53, "elapsed_time": "0:03:42", "remaining_time": "0:45:30"}
{"current_steps": 8, "total_steps": 93, "loss": 0.7703, "lr": 1.6000000000000003e-05, "epoch": 0.256, "percentage": 8.6, "elapsed_time": "0:04:18", "remaining_time": "0:45:42"}
{"current_steps": 9, "total_steps": 93, "loss": 0.7283, "lr": 1.8e-05, "epoch": 0.288, "percentage": 9.68, "elapsed_time": "0:04:49", "remaining_time": "0:45:05"}
{"current_steps": 10, "total_steps": 93, "loss": 0.7136, "lr": 2e-05, "epoch": 0.32, "percentage": 10.75, "elapsed_time": "0:05:17", "remaining_time": "0:43:55"}
{"current_steps": 11, "total_steps": 93, "loss": 0.7436, "lr": 1.9992837548163315e-05, "epoch": 0.352, "percentage": 11.83, "elapsed_time": "0:05:51", "remaining_time": "0:43:38"}
{"current_steps": 12, "total_steps": 93, "loss": 0.6954, "lr": 1.9971360452796523e-05, "epoch": 0.384, "percentage": 12.9, "elapsed_time": "0:06:21", "remaining_time": "0:42:52"}
{"current_steps": 13, "total_steps": 93, "loss": 0.6304, "lr": 1.993559947963185e-05, "epoch": 0.416, "percentage": 13.98, "elapsed_time": "0:06:57", "remaining_time": "0:42:48"}
{"current_steps": 14, "total_steps": 93, "loss": 0.661, "lr": 1.9885605855918887e-05, "epoch": 0.448, "percentage": 15.05, "elapsed_time": "0:07:18", "remaining_time": "0:41:14"}
{"current_steps": 15, "total_steps": 93, "loss": 0.621, "lr": 1.9821451197042028e-05, "epoch": 0.48, "percentage": 16.13, "elapsed_time": "0:07:43", "remaining_time": "0:40:12"}
{"current_steps": 16, "total_steps": 93, "loss": 0.6491, "lr": 1.9743227403932135e-05, "epoch": 0.512, "percentage": 17.2, "elapsed_time": "0:08:30", "remaining_time": "0:40:58"}
{"current_steps": 17, "total_steps": 93, "loss": 0.6351, "lr": 1.9651046531419335e-05, "epoch": 0.544, "percentage": 18.28, "elapsed_time": "0:09:08", "remaining_time": "0:40:52"}
{"current_steps": 18, "total_steps": 93, "loss": 0.6125, "lr": 1.9545040627715554e-05, "epoch": 0.576, "percentage": 19.35, "elapsed_time": "0:09:39", "remaining_time": "0:40:16"}
{"current_steps": 19, "total_steps": 93, "loss": 0.6397, "lr": 1.942536154525673e-05, "epoch": 0.608, "percentage": 20.43, "elapsed_time": "0:10:07", "remaining_time": "0:39:26"}
{"current_steps": 20, "total_steps": 93, "loss": 0.5623, "lr": 1.9292180723175656e-05, "epoch": 0.64, "percentage": 21.51, "elapsed_time": "0:10:36", "remaining_time": "0:38:42"}
{"current_steps": 21, "total_steps": 93, "loss": 0.5951, "lr": 1.9145688941717074e-05, "epoch": 0.672, "percentage": 22.58, "elapsed_time": "0:11:13", "remaining_time": "0:38:29"}
{"current_steps": 22, "total_steps": 93, "loss": 0.6159, "lr": 1.8986096048946826e-05, "epoch": 0.704, "percentage": 23.66, "elapsed_time": "0:11:46", "remaining_time": "0:38:00"}
{"current_steps": 23, "total_steps": 93, "loss": 0.5522, "lr": 1.881363066014649e-05, "epoch": 0.736, "percentage": 24.73, "elapsed_time": "0:12:13", "remaining_time": "0:37:12"}
{"current_steps": 24, "total_steps": 93, "loss": 0.6563, "lr": 1.862853983032423e-05, "epoch": 0.768, "percentage": 25.81, "elapsed_time": "0:12:47", "remaining_time": "0:36:47"}
{"current_steps": 25, "total_steps": 93, "loss": 0.5965, "lr": 1.8431088700310846e-05, "epoch": 0.8, "percentage": 26.88, "elapsed_time": "0:13:21", "remaining_time": "0:36:19"}
{"current_steps": 26, "total_steps": 93, "loss": 0.6577, "lr": 1.8221560116948103e-05, "epoch": 0.832, "percentage": 27.96, "elapsed_time": "0:14:01", "remaining_time": "0:36:09"}
{"current_steps": 27, "total_steps": 93, "loss": 0.5977, "lr": 1.8000254227913346e-05, "epoch": 0.864, "percentage": 29.03, "elapsed_time": "0:14:33", "remaining_time": "0:35:35"}
{"current_steps": 28, "total_steps": 93, "loss": 0.5929, "lr": 1.7767488051760858e-05, "epoch": 0.896, "percentage": 30.11, "elapsed_time": "0:15:04", "remaining_time": "0:35:00"}
{"current_steps": 29, "total_steps": 93, "loss": 0.6165, "lr": 1.7523595023795814e-05, "epoch": 0.928, "percentage": 31.18, "elapsed_time": "0:15:38", "remaining_time": "0:34:31"}
{"current_steps": 30, "total_steps": 93, "loss": 0.6351, "lr": 1.7268924518431437e-05, "epoch": 0.96, "percentage": 32.26, "elapsed_time": "0:16:15", "remaining_time": "0:34:07"}
{"current_steps": 31, "total_steps": 93, "loss": 0.5994, "lr": 1.700384134871351e-05, "epoch": 0.992, "percentage": 33.33, "elapsed_time": "0:16:45", "remaining_time": "0:33:31"}
{"current_steps": 32, "total_steps": 93, "loss": 0.8536, "lr": 1.672872524372919e-05, "epoch": 1.024, "percentage": 34.41, "elapsed_time": "0:18:18", "remaining_time": "0:34:54"}
{"current_steps": 33, "total_steps": 93, "loss": 0.4804, "lr": 1.644397030464877e-05, "epoch": 1.056, "percentage": 35.48, "elapsed_time": "0:18:55", "remaining_time": "0:34:25"}
{"current_steps": 34, "total_steps": 93, "loss": 0.4955, "lr": 1.614998444017954e-05, "epoch": 1.088, "percentage": 36.56, "elapsed_time": "0:19:27", "remaining_time": "0:33:45"}
{"current_steps": 35, "total_steps": 93, "loss": 0.5212, "lr": 1.5847188782240473e-05, "epoch": 1.12, "percentage": 37.63, "elapsed_time": "0:19:54", "remaining_time": "0:32:59"}
{"current_steps": 36, "total_steps": 93, "loss": 0.4318, "lr": 1.5536017082694846e-05, "epoch": 1.152, "percentage": 38.71, "elapsed_time": "0:20:27", "remaining_time": "0:32:23"}
{"current_steps": 37, "total_steps": 93, "loss": 0.5298, "lr": 1.5216915092004847e-05, "epoch": 1.184, "percentage": 39.78, "elapsed_time": "0:21:08", "remaining_time": "0:31:59"}
{"current_steps": 38, "total_steps": 93, "loss": 0.5354, "lr": 1.4890339920698334e-05, "epoch": 1.216, "percentage": 40.86, "elapsed_time": "0:21:45", "remaining_time": "0:31:29"}
{"current_steps": 39, "total_steps": 93, "loss": 0.4242, "lr": 1.4556759384562418e-05, "epoch": 1.248, "percentage": 41.94, "elapsed_time": "0:22:19", "remaining_time": "0:30:54"}
{"current_steps": 40, "total_steps": 93, "loss": 0.4599, "lr": 1.421665133450184e-05, "epoch": 1.28, "percentage": 43.01, "elapsed_time": "0:22:48", "remaining_time": "0:30:12"}
{"current_steps": 41, "total_steps": 93, "loss": 0.4125, "lr": 1.3870502972022175e-05, "epoch": 1.312, "percentage": 44.09, "elapsed_time": "0:23:17", "remaining_time": "0:29:32"}
{"current_steps": 42, "total_steps": 93, "loss": 0.5169, "lr": 1.351881015131833e-05, "epoch": 1.3439999999999999, "percentage": 45.16, "elapsed_time": "0:23:59", "remaining_time": "0:29:07"}
{"current_steps": 43, "total_steps": 93, "loss": 0.4106, "lr": 1.316207666896824e-05, "epoch": 1.376, "percentage": 46.24, "elapsed_time": "0:24:34", "remaining_time": "0:28:34"}
{"current_steps": 44, "total_steps": 93, "loss": 0.5101, "lr": 1.2800813542249073e-05, "epoch": 1.408, "percentage": 47.31, "elapsed_time": "0:25:04", "remaining_time": "0:27:55"}
{"current_steps": 45, "total_steps": 93, "loss": 0.5469, "lr": 1.2435538277109919e-05, "epoch": 1.44, "percentage": 48.39, "elapsed_time": "0:25:38", "remaining_time": "0:27:21"}
{"current_steps": 46, "total_steps": 93, "loss": 0.4318, "lr": 1.206677412684953e-05, "epoch": 1.472, "percentage": 49.46, "elapsed_time": "0:26:07", "remaining_time": "0:26:41"}
{"current_steps": 47, "total_steps": 93, "loss": 0.4563, "lr": 1.1695049342560969e-05, "epoch": 1.504, "percentage": 50.54, "elapsed_time": "0:26:40", "remaining_time": "0:26:06"}
{"current_steps": 48, "total_steps": 93, "loss": 0.5076, "lr": 1.1320896416417026e-05, "epoch": 1.536, "percentage": 51.61, "elapsed_time": "0:27:13", "remaining_time": "0:25:31"}
{"current_steps": 49, "total_steps": 93, "loss": 0.516, "lr": 1.0944851318880314e-05, "epoch": 1.568, "percentage": 52.69, "elapsed_time": "0:27:47", "remaining_time": "0:24:57"}
{"current_steps": 50, "total_steps": 93, "loss": 0.462, "lr": 1.0567452730930743e-05, "epoch": 1.6, "percentage": 53.76, "elapsed_time": "0:28:21", "remaining_time": "0:24:23"}
{"current_steps": 51, "total_steps": 93, "loss": 0.4514, "lr": 1.0189241272410191e-05, "epoch": 1.6320000000000001, "percentage": 54.84, "elapsed_time": "0:28:49", "remaining_time": "0:23:44"}
{"current_steps": 52, "total_steps": 93, "loss": 0.5001, "lr": 9.810758727589814e-06, "epoch": 1.6640000000000001, "percentage": 55.91, "elapsed_time": "0:29:17", "remaining_time": "0:23:05"}
{"current_steps": 53, "total_steps": 93, "loss": 0.4482, "lr": 9.43254726906926e-06, "epoch": 1.696, "percentage": 56.99, "elapsed_time": "0:29:43", "remaining_time": "0:22:26"}
{"current_steps": 54, "total_steps": 93, "loss": 0.4322, "lr": 9.055148681119688e-06, "epoch": 1.728, "percentage": 58.06, "elapsed_time": "0:30:21", "remaining_time": "0:21:55"}
{"current_steps": 55, "total_steps": 93, "loss": 0.4316, "lr": 8.67910358358298e-06, "epoch": 1.76, "percentage": 59.14, "elapsed_time": "0:30:52", "remaining_time": "0:21:20"}
{"current_steps": 56, "total_steps": 93, "loss": 0.4805, "lr": 8.304950657439034e-06, "epoch": 1.792, "percentage": 60.22, "elapsed_time": "0:31:20", "remaining_time": "0:20:42"}
{"current_steps": 57, "total_steps": 93, "loss": 0.433, "lr": 7.93322587315047e-06, "epoch": 1.8239999999999998, "percentage": 61.29, "elapsed_time": "0:31:51", "remaining_time": "0:20:07"}
{"current_steps": 58, "total_steps": 93, "loss": 0.4647, "lr": 7.564461722890082e-06, "epoch": 1.8559999999999999, "percentage": 62.37, "elapsed_time": "0:32:20", "remaining_time": "0:19:31"}
{"current_steps": 59, "total_steps": 93, "loss": 0.3784, "lr": 7.199186457750931e-06, "epoch": 1.888, "percentage": 63.44, "elapsed_time": "0:32:41", "remaining_time": "0:18:50"}
{"current_steps": 60, "total_steps": 93, "loss": 0.4661, "lr": 6.837923331031761e-06, "epoch": 1.92, "percentage": 64.52, "elapsed_time": "0:33:15", "remaining_time": "0:18:17"}
{"current_steps": 61, "total_steps": 93, "loss": 0.4882, "lr": 6.48118984868167e-06, "epoch": 1.952, "percentage": 65.59, "elapsed_time": "0:33:48", "remaining_time": "0:17:44"}
{"current_steps": 62, "total_steps": 93, "loss": 0.4669, "lr": 6.129497027977829e-06, "epoch": 1.984, "percentage": 66.67, "elapsed_time": "0:34:23", "remaining_time": "0:17:11"}
{"current_steps": 63, "total_steps": 93, "loss": 0.6206, "lr": 5.78334866549816e-06, "epoch": 2.016, "percentage": 67.74, "elapsed_time": "0:36:01", "remaining_time": "0:17:09"}
{"current_steps": 64, "total_steps": 93, "loss": 0.3816, "lr": 5.443240615437586e-06, "epoch": 2.048, "percentage": 68.82, "elapsed_time": "0:36:28", "remaining_time": "0:16:31"}
{"current_steps": 65, "total_steps": 93, "loss": 0.402, "lr": 5.109660079301668e-06, "epoch": 2.08, "percentage": 69.89, "elapsed_time": "0:36:52", "remaining_time": "0:15:53"}
{"current_steps": 66, "total_steps": 93, "loss": 0.3663, "lr": 4.783084907995156e-06, "epoch": 2.112, "percentage": 70.97, "elapsed_time": "0:37:16", "remaining_time": "0:15:14"}
{"current_steps": 67, "total_steps": 93, "loss": 0.3979, "lr": 4.463982917305155e-06, "epoch": 2.144, "percentage": 72.04, "elapsed_time": "0:37:53", "remaining_time": "0:14:42"}
{"current_steps": 68, "total_steps": 93, "loss": 0.2757, "lr": 4.152811217759529e-06, "epoch": 2.176, "percentage": 73.12, "elapsed_time": "0:38:25", "remaining_time": "0:14:07"}
{"current_steps": 69, "total_steps": 93, "loss": 0.3429, "lr": 3.850015559820465e-06, "epoch": 2.208, "percentage": 74.19, "elapsed_time": "0:38:57", "remaining_time": "0:13:32"}
{"current_steps": 70, "total_steps": 93, "loss": 0.3981, "lr": 3.5560296953512296e-06, "epoch": 2.24, "percentage": 75.27, "elapsed_time": "0:39:27", "remaining_time": "0:12:58"}
{"current_steps": 71, "total_steps": 93, "loss": 0.37, "lr": 3.2712747562708115e-06, "epoch": 2.2720000000000002, "percentage": 76.34, "elapsed_time": "0:39:55", "remaining_time": "0:12:22"}
{"current_steps": 72, "total_steps": 93, "loss": 0.4165, "lr": 2.9961586512864947e-06, "epoch": 2.304, "percentage": 77.42, "elapsed_time": "0:40:26", "remaining_time": "0:11:47"}
{"current_steps": 73, "total_steps": 93, "loss": 0.3389, "lr": 2.7310754815685627e-06, "epoch": 2.336, "percentage": 78.49, "elapsed_time": "0:40:56", "remaining_time": "0:11:13"}
{"current_steps": 74, "total_steps": 93, "loss": 0.3643, "lr": 2.4764049762041874e-06, "epoch": 2.368, "percentage": 79.57, "elapsed_time": "0:41:31", "remaining_time": "0:10:39"}
{"current_steps": 75, "total_steps": 93, "loss": 0.2996, "lr": 2.2325119482391466e-06, "epoch": 2.4, "percentage": 80.65, "elapsed_time": "0:41:59", "remaining_time": "0:10:04"}
{"current_steps": 76, "total_steps": 93, "loss": 0.4327, "lr": 1.9997457720866554e-06, "epoch": 2.432, "percentage": 81.72, "elapsed_time": "0:42:32", "remaining_time": "0:09:30"}
{"current_steps": 77, "total_steps": 93, "loss": 0.315, "lr": 1.7784398830519002e-06, "epoch": 2.464, "percentage": 82.8, "elapsed_time": "0:42:59", "remaining_time": "0:08:56"}
{"current_steps": 78, "total_steps": 93, "loss": 0.343, "lr": 1.5689112996891576e-06, "epoch": 2.496, "percentage": 83.87, "elapsed_time": "0:43:43", "remaining_time": "0:08:24"}
{"current_steps": 79, "total_steps": 93, "loss": 0.3484, "lr": 1.3714601696757713e-06, "epoch": 2.528, "percentage": 84.95, "elapsed_time": "0:44:17", "remaining_time": "0:07:51"}
{"current_steps": 80, "total_steps": 93, "loss": 0.4159, "lr": 1.1863693398535115e-06, "epoch": 2.56, "percentage": 86.02, "elapsed_time": "0:44:41", "remaining_time": "0:07:15"}
{"current_steps": 81, "total_steps": 93, "loss": 0.384, "lr": 1.01390395105318e-06, "epoch": 2.592, "percentage": 87.1, "elapsed_time": "0:45:10", "remaining_time": "0:06:41"}
{"current_steps": 82, "total_steps": 93, "loss": 0.3486, "lr": 8.543110582829272e-07, "epoch": 2.624, "percentage": 88.17, "elapsed_time": "0:45:40", "remaining_time": "0:06:07"}
{"current_steps": 83, "total_steps": 93, "loss": 0.3445, "lr": 7.078192768243486e-07, "epoch": 2.656, "percentage": 89.25, "elapsed_time": "0:46:15", "remaining_time": "0:05:34"}
{"current_steps": 84, "total_steps": 93, "loss": 0.3915, "lr": 5.746384547432738e-07, "epoch": 2.6879999999999997, "percentage": 90.32, "elapsed_time": "0:46:59", "remaining_time": "0:05:02"}
{"current_steps": 85, "total_steps": 93, "loss": 0.4302, "lr": 4.549593722844492e-07, "epoch": 2.7199999999999998, "percentage": 91.4, "elapsed_time": "0:47:33", "remaining_time": "0:04:28"}
{"current_steps": 86, "total_steps": 93, "loss": 0.2589, "lr": 3.4895346858066723e-07, "epoch": 2.752, "percentage": 92.47, "elapsed_time": "0:48:07", "remaining_time": "0:03:55"}
{"current_steps": 87, "total_steps": 93, "loss": 0.3742, "lr": 2.5677259606786686e-07, "epoch": 2.784, "percentage": 93.55, "elapsed_time": "0:48:42", "remaining_time": "0:03:21"}
{"current_steps": 88, "total_steps": 93, "loss": 0.3535, "lr": 1.7854880295797406e-07, "epoch": 2.816, "percentage": 94.62, "elapsed_time": "0:49:08", "remaining_time": "0:02:47"}
{"current_steps": 89, "total_steps": 93, "loss": 0.3458, "lr": 1.1439414408111471e-07, "epoch": 2.848, "percentage": 95.7, "elapsed_time": "0:49:34", "remaining_time": "0:02:13"}
{"current_steps": 90, "total_steps": 93, "loss": 0.4665, "lr": 6.440052036815081e-08, "epoch": 2.88, "percentage": 96.77, "elapsed_time": "0:50:10", "remaining_time": "0:01:40"}
{"current_steps": 91, "total_steps": 93, "loss": 0.3022, "lr": 2.86395472034795e-08, "epoch": 2.912, "percentage": 97.85, "elapsed_time": "0:50:43", "remaining_time": "0:01:06"}
{"current_steps": 92, "total_steps": 93, "loss": 0.3701, "lr": 7.162451836685291e-09, "epoch": 2.944, "percentage": 98.92, "elapsed_time": "0:51:12", "remaining_time": "0:00:33"}
{"current_steps": 93, "total_steps": 93, "loss": 0.295, "lr": 0.0, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "0:51:38", "remaining_time": "0:00:00"}
{"current_steps": 93, "total_steps": 93, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "0:53:56", "remaining_time": "0:00:00"}